Convergence Analysis of Complementary Candid Incremental Principal Component Analysis ∗
暂无分享，去创建一个
In this report, we analyze a proposed incremental principal component analysis algorithm, complementary candid incremental PCA algorithm, and prove that, following this algorithm, the estimated vectors vi(n) converge to λiei when n →∞, with probability 1.
[1] Harold J. Kushner,et al. wchastic. approximation methods for constrained and unconstrained systems , 1978 .
[2] Erkki Oja,et al. Subspace methods of pattern recognition , 1983 .
[3] E. Oja,et al. On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix , 1985 .
[4] Terence D. Sanger,et al. Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.